DATA ANALYSIS

Use of PGRs to Reduce Seed Shattering in Perennial Ryegrass (PGF A415-6 Greenhouse Summer 2021)

This report contains the data analysis from the 2021 PGR greenshouse in PGF. The data was collected in 2021. This file is a combination of field data (growth, harvest, and shattering).

This file has been written as a Jupyter Notebook.

import numpy as np
import pandas as pd

# ggplot's cousin
from plotnine import *

from matplotlib import pyplot as plt
from matplotlib import cm

import seaborn as sns


# import joypy       # For ridgeline plots

# Make sure Jupyter Notebook shows all outputs from the same cell
from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"

# Set max number of rows to visualize
pd.set_option('display.max_rows', 10)

# plt.rcParams['figure.figsize'] = [12, 8]
plt.rcParams['figure.dpi'] = 80

flip_xlabels = theme(axis_text_x = element_text(angle=90, hjust=1))

Field Data

FD = pd.read_csv ('.\CURATED\PGRGH2021_FieldData_Compiled.csv')
print(FD.columns)
FD

Index(['Block', 'Plot', 'Tray', 'Treatment', 'VisShatt', 'Range',
       'Shaken_SPKS', 'Pre-Detached_SEED', 'TOTAL_Undetached', 'Detached_SEED',
       'Undetached_SEED', 'NotesShake', 'AVG_Shatt_SPK', 'AVG_Retent_SPK',
       'AVG_AdjShatt_SPK', 'POT_Yld_SPK', 'PCTG_YldLoss', 'PCTG_YldLoss_SPK',
       'Dry_Unthreshed', 'Dry_Threshed', 'NotesDry', 'WET_wgt', 'SMC_Unthr',
       'Est_Debris', 'Column', 'Row', 'G1_Apr07', 'G2_Apr16', 'G3_Apr19',
       'G4_Apr21', 'G5_Apr23', 'G6_Apr28', 'G7_May03', 'Tallest',
       'AverageHeight', 'AUC_Gust'],
      dtype='object')

	Block	Plot	Tray	Treatment	VisShatt	Range	Shaken_SPKS	Pre-Detached_SEED	TOTAL_Undetached	Detached_SEED	...	G1_Apr07	G2_Apr16	G3_Apr19	G4_Apr21	G5_Apr23	G6_Apr28	G7_May03	Tallest	AverageHeight	AUC_Gust
0	B2	p0391	21	T1:Water	2.5	5.0	12.0	0.118	0.782	0.122	...	31.0	45.0	53.0	55.0	58.0	65.0	65.0	48.0	36	207.607428
1	B2	p0615	35	T1:Water	2.5	5.0	12.0	0.019	0.655	0.027	...	45.0	56.0	61.0	65.0	65.0	65.0	69.0	64.0	50	210.385206
2	B2	p0655	39	T1:Water	2.5	5.0	12.0	0.057	0.764	0.045	...	45.0	56.0	59.0	65.0	65.0	65.0	69.0	61.0	42	210.385206
3	B2	p0647	36	T1:Water	5.0	10.0	12.0	0.035	0.816	0.060	...	45.0	45.0	52.0	57.0	59.0	65.0	69.0	56.0	45	209.162984
4	B2	p0445	24	T1:Water	2.5	5.0	12.0	0.012	0.739	0.026	...	40.0	45.0	45.0	52.0	57.0	59.0	69.0	66.0	52	208.607428
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
123	B2	p0643	40	T1:Water	6.5	7.0	13.0	0.184	1.040	0.133	...	45.0	51.0	54.0	57.0	59.0	65.0	65.0	68.0	52	209.829650
124	B3	p1009	57	T1:Water	1.5	3.0	12.0	0.020	0.590	0.005	...	31.0	45.0	52.0	52.0	54.0	65.0	69.0	65.0	51	207.607428
125	B3	p0925	54	T1:Water	1.0	2.0	12.0	0.019	1.445	0.016	...	31.0	45.0	52.0	57.0	59.0	59.0	65.0	86.0	69	207.607428
126	B3	p1079	60	T1:Water	2.5	5.0	12.0	0.000	0.488	0.008	...	45.0	57.0	58.0	65.0	65.0	69.0	69.0	55.0	44	210.496317
127	B3	p1075	59	T1:Water	15.0	10.0	14.0	0.042	0.500	0.020	...	40.0	52.0	57.0	65.0	65.0	65.0	69.0	54.0	43	209.385206

128 rows × 36 columns

Values Count

FD_gb = FD.groupby(['Block', 'Treatment']).size().unstack(level=0)
# FD_gb = FD.groupby(['Treatment']).size()
FD_gb.plot(kind = 'bar')

<AxesSubplot:xlabel='Treatment'>

FD.groupby(['Block', 'Treatment'])['SMC_Unthr'].describe()

		count	mean	std	min	25%	50%	75%	max
Block	Treatment
B2	T1:Water	8.0	0.103546	0.021349	0.075435	0.091212	0.097068	0.116925	0.136792
	T2:AVG_Low	7.0	0.097835	0.035751	0.069231	0.078321	0.086460	0.098755	0.175000
	T3:AVG_Med	7.0	0.056747	0.021020	0.029070	0.042679	0.048649	0.076505	0.081140
	T4:AVG_High	6.0	0.082693	0.016517	0.062857	0.074353	0.081088	0.085845	0.111588
	T5:ETH	2.0	0.094404	0.012288	0.085714	0.090059	0.094404	0.098748	0.103093
...	...	...	...	...	...	...	...	...	...
B3	T4:AVG_High	9.0	0.068055	0.059071	-0.080000	0.072238	0.082892	0.088268	0.130000
	T6:PrhxCa_Low	9.0	0.117396	0.042129	0.078086	0.087379	0.115966	0.126050	0.217391
	T7:PrhxCa_Med	11.0	0.123009	0.095911	0.039823	0.085390	0.093168	0.108024	0.386364
	T8:PrhxCa_High	11.0	0.172807	0.278956	0.000000	0.068294	0.091837	0.134592	1.000000
	T9:GA3	7.0	0.089699	0.022732	0.048023	0.078820	0.099668	0.104786	0.112994

17 rows × 8 columns

ggplot(FD, aes(x='Block', y='SMC_Unthr', fill = 'Treatment')) + geom_boxplot() + flip_xlabels
# ggplot(FD, aes(x='Block', y=FD['SMC_Unthr'], fill = 'Treatment')) + geom_boxplot() + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 2 rows containing non-finite values.

<ggplot: (129429225186)>

ggplot(FD, aes(x='Block', y=np.log10(FD['AVG_Shatt_SPK']+1), fill = 'Treatment')) + geom_boxplot() + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 1 rows containing non-finite values.

<ggplot: (129429048483)>

# FD.droplevel('Treatment'=="T1:Water")
FD[FD["Treatment"]!="T5:ETH"]

	Block	Plot	Tray	Treatment	VisShatt	Range	Shaken_SPKS	Pre-Detached_SEED	TOTAL_Undetached	Detached_SEED	...	G1_Apr07	G2_Apr16	G3_Apr19	G4_Apr21	G5_Apr23	G6_Apr28	G7_May03	Tallest	AverageHeight	AUC_Gust
0	B2	p0391	21	T1:Water	2.5	5.0	12.0	0.118	0.782	0.122	...	31.0	45.0	53.0	55.0	58.0	65.0	65.0	48.0	36	207.607428
1	B2	p0615	35	T1:Water	2.5	5.0	12.0	0.019	0.655	0.027	...	45.0	56.0	61.0	65.0	65.0	65.0	69.0	64.0	50	210.385206
2	B2	p0655	39	T1:Water	2.5	5.0	12.0	0.057	0.764	0.045	...	45.0	56.0	59.0	65.0	65.0	65.0	69.0	61.0	42	210.385206
3	B2	p0647	36	T1:Water	5.0	10.0	12.0	0.035	0.816	0.060	...	45.0	45.0	52.0	57.0	59.0	65.0	69.0	56.0	45	209.162984
4	B2	p0445	24	T1:Water	2.5	5.0	12.0	0.012	0.739	0.026	...	40.0	45.0	45.0	52.0	57.0	59.0	69.0	66.0	52	208.607428
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
123	B2	p0643	40	T1:Water	6.5	7.0	13.0	0.184	1.040	0.133	...	45.0	51.0	54.0	57.0	59.0	65.0	65.0	68.0	52	209.829650
124	B3	p1009	57	T1:Water	1.5	3.0	12.0	0.020	0.590	0.005	...	31.0	45.0	52.0	52.0	54.0	65.0	69.0	65.0	51	207.607428
125	B3	p0925	54	T1:Water	1.0	2.0	12.0	0.019	1.445	0.016	...	31.0	45.0	52.0	57.0	59.0	59.0	65.0	86.0	69	207.607428
126	B3	p1079	60	T1:Water	2.5	5.0	12.0	0.000	0.488	0.008	...	45.0	57.0	58.0	65.0	65.0	69.0	69.0	55.0	44	210.496317
127	B3	p1075	59	T1:Water	15.0	10.0	14.0	0.042	0.500	0.020	...	40.0	52.0	57.0	65.0	65.0	65.0	69.0	54.0	43	209.385206

126 rows × 36 columns

# ggplot(FD, aes(x='Treatment', y=np.log10(FD['AVG_Retent_SPK']+1), fill = 'Block')) + geom_boxplot() + facet_grid('~Block') + flip_xlabels
ggplot(FD, aes(x='Block', y=np.log10(FD['AVG_Retent_SPK']+1), fill = 'Treatment')) + geom_boxplot() + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 1 rows containing non-finite values.

<ggplot: (129428878349)>

# ggplot(FD, aes(x='Treatment', y=np.log10(FD['AVG_AdjShatt_SPK']+1), fill = 'Block')) + geom_boxplot() + facet_grid('~Block') + flip_xlabels
ggplot(FD, aes(x='Block', y=np.log10(FD['AVG_AdjShatt_SPK']+1), fill = 'Treatment')) + geom_boxplot() + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 1 rows containing non-finite values.

<ggplot: (129429222789)>

# ggplot(FD, aes(x='Treatment', y=np.log10(FD['POT_Yld_SPK']+1), fill = 'Block')) + geom_boxplot() + facet_grid('~Block') + flip_xlabels
ggplot(FD, aes(x='Block', y=np.log10(FD['POT_Yld_SPK']+1), fill = 'Treatment')) + geom_boxplot() + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 1 rows containing non-finite values.

<ggplot: (129430979069)>

# ggplot(FD, aes(x='Treatment', y=np.log10(FD['PCTG_YldLoss']+1), fill = 'Block')) + geom_boxplot() + facet_grid('~Block') + flip_xlabels
ggplot(FD, aes(x='Block', y=np.log10(FD['PCTG_YldLoss']+1), fill = 'Treatment')) + geom_boxplot() + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 1 rows containing non-finite values.

<ggplot: (129428874493)>

# ggplot(FD, aes(x='Treatment', y=np.log10(FD['PCTG_YldLoss_SPK']+1), fill = 'Block')) + geom_boxplot() + facet_grid('~Block') + flip_xlabels
ggplot(FD, aes(x='Block', y=np.log10(FD['PCTG_YldLoss_SPK']+1), fill = 'Treatment')) + geom_boxplot() + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 1 rows containing non-finite values.

<ggplot: (129428920167)>

FD.columns

Index(['Block', 'Plot', 'Tray', 'Treatment', 'VisShatt', 'Range',
       'Shaken_SPKS', 'Pre-Detached_SEED', 'TOTAL_Undetached', 'Detached_SEED',
       'Undetached_SEED', 'NotesShake', 'AVG_Shatt_SPK', 'AVG_Retent_SPK',
       'AVG_AdjShatt_SPK', 'POT_Yld_SPK', 'PCTG_YldLoss', 'PCTG_YldLoss_SPK',
       'Dry_Unthreshed', 'Dry_Threshed', 'NotesDry', 'WET_wgt', 'SMC_Unthr',
       'Est_Debris', 'Column', 'Row', 'G1_Apr07', 'G2_Apr16', 'G3_Apr19',
       'G4_Apr21', 'G5_Apr23', 'G6_Apr28', 'G7_May03', 'Tallest',
       'AverageHeight', 'AUC_Gust'],
      dtype='object')

# Subset the data
# FD.columns.get_loc('AVG_AdjShatt_SPK')

# SubFD = FD.iloc[:, np.r_[0,2,15:19,23:26]]
# SubFD

SubFD = FD[['Block', 'Plot', 'Tray', 'Treatment','AVG_Shatt_SPK', 
            'AVG_Retent_SPK','AVG_AdjShatt_SPK', 'POT_Yld_SPK', 
            'PCTG_YldLoss', 'PCTG_YldLoss_SPK','WET_wgt','SMC_Unthr','Est_Debris','Tallest',
       'AverageHeight', 'AUC_Gust']]

ToLog = ['AVG_Shatt_SPK', 'AVG_Retent_SPK','AVG_AdjShatt_SPK', 'POT_Yld_SPK', 'PCTG_YldLoss', 'PCTG_YldLoss_SPK','WET_wgt','SMC_Unthr']

LogSubFD = SubFD[ToLog].applymap(lambda x: np.log10(x+1))
# LogSubFD

SubFD = SubFD.drop(ToLog, axis=1)
# SubFD

LogSubFD = pd.concat([SubFD.reset_index(drop=True), LogSubFD], axis=1)
LogSubFD

	Block	Plot	Tray	Treatment	Est_Debris	Tallest	AverageHeight	AUC_Gust	AVG_Shatt_SPK	AVG_Retent_SPK	AVG_AdjShatt_SPK	POT_Yld_SPK	PCTG_YldLoss	PCTG_YldLoss_SPK	WET_wgt	SMC_Unthr
0	B2	p0391	21	T1:Water	0.115702	48.0	36	207.607428	0.008600	0.010512	0.010371	0.020637	0.111934	0.010512	0.185825	0.038872
1	B2	p0615	35	T1:Water	0.125683	64.0	50	210.385206	0.001662	0.005967	0.002007	0.007946	0.066699	0.005967	0.083503	0.055681
2	B2	p0655	39	T1:Water	0.217877	61.0	42	210.385206	0.003676	0.003496	0.004438	0.007899	0.040207	0.003496	0.078819	0.041591
3	B2	p0647	36	T1:Water	0.138462	56.0	45	209.162984	0.003425	0.011852	0.004844	0.016566	0.124504	0.011852	0.154424	0.036090
4	B2	p0445	24	T1:Water	0.155797	66.0	52	208.607428	0.001373	0.009769	0.001659	0.011391	0.104828	0.009769	0.117603	0.046316
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
123	B2	p0643	40	T1:Water	0.244770	68.0	52	209.829650	0.010463	0.006631	0.015602	0.022000	0.079181	0.006631	0.180986	0.031584
124	B3	p1009	57	T1:Water	0.128049	65.0	51	207.607428	0.000904	0.005502	0.001017	0.006506	0.061829	0.005502	0.071145	0.032881
125	B3	p0925	54	T1:Water	0.084211	86.0	69	207.607428	0.001265	0.020568	0.001370	0.021875	0.199206	0.020568	0.208710	0.031883
126	B3	p1079	60	T1:Water	0.421053	55.0	44	210.496317	0.000289	0.000615	0.000350	0.000964	0.007321	0.000615	0.010724	0.093422
127	B3	p1075	59	T1:Water	0.148148	54.0	43	209.385206	0.001919	0.001610	0.003966	0.005561	0.022016	0.001610	0.046885	0.022276

128 rows × 16 columns

%%time
sns.pairplot(LogSubFD, hue="Treatment")

Wall time: 1min 1s

<seaborn.axisgrid.PairGrid at 0x1e230dc21f0>

%%time
sns.pairplot(LogSubFD, hue="Block")

Wall time: 50 s

<seaborn.axisgrid.PairGrid at 0x1e2380dac70>

Chlorophyll Content

Chlo = pd.read_csv ('.\CURATED\PGRGH2021_Chloph_Compiled.csv')
print(Chlo.columns)
Chlo

Index(['Block', 'Plot', 'Tray', 'Column', 'Row', 'Treatment', 'G1_Apr07',
       'G2_Apr16', 'G3_Apr19', 'G4_Apr21', 'G5_Apr23', 'G6_Apr28', 'G7_May03',
       'Tallest', 'AverageHeight', 'F700_Lvl_1', 'F735_Lvl_1', 'CFR_1',
       'Concentration_1', 'F700_Lvl_2', 'F735_Lvl_2', 'CFR_2',
       'Concentration_2', 'Rep', 'VisShatt', 'Range', 'Shaken_SPKS',
       'Pre-Detached_SEED', 'TOTAL_Undetached', 'Detached_SEED',
       'Undetached_SEED', 'NotesShake', 'AVG_Shatt_SPK', 'AVG_Retent_SPK',
       'AVG_AdjShatt_SPK', 'POT_Yld_SPK', 'PCTG_YldLoss', 'PCTG_YldLoss_SPK',
       'Dry_Unthreshed', 'Dry_Threshed', 'NotesDry', 'WET_wgt', 'SMC_Unthr',
       'Est_Debris', 'AUC_Gust'],
      dtype='object')

	Block	Plot	Tray	Column	Row	Treatment	G1_Apr07	G2_Apr16	G3_Apr19	G4_Apr21	...	POT_Yld_SPK	PCTG_YldLoss	PCTG_YldLoss_SPK	Dry_Unthreshed	Dry_Threshed	NotesDry	WET_wgt	SMC_Unthr	Est_Debris	AUC_Gust
0	B1	p0109	7	4	8	T2:AVG_Low	32	45	45	54	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	207.718539
1	B1	p0109	7	4	8	T2:AVG_Low	32	45	45	54	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	207.718539
2	B1	p0109	7	4	8	T2:AVG_Low	32	45	45	54	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	207.718539
3	B1	p0139	7	4	10	T7:PrhxCa_Med	40	53	55	65	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	209.496317
4	B1	p0139	7	4	10	T7:PrhxCa_Med	40	53	55	65	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	209.496317
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
238	B3	p0939	53	9	15	T1:Water	40	52	61	65	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	209.385206
239	B3	p0939	53	9	15	T1:Water	40	52	61	65	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	209.385206
240	B3	p0969	53	9	17	T8:PrhxCa_High	40	45	52	52	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	208.607428
241	B3	p0969	53	9	17	T8:PrhxCa_High	40	45	52	52	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	208.607428
242	B3	p0969	53	9	17	T8:PrhxCa_High	40	45	52	52	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	208.607428

243 rows × 45 columns

ggplot(Chlo, aes(x='Treatment', y=Chlo['Concentration_1'], fill = 'Treatment')) + geom_boxplot(aes(x='Treatment', y=Chlo['Concentration_1'])) + facet_grid('Block~') + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 27 rows containing non-finite values.

<ggplot: (129525288837)>

ggplot(Chlo, aes(x='Treatment', y=Chlo['Concentration_1'], fill = 'Treatment')) + geom_boxplot(aes(x='Treatment', y=Chlo['Concentration_1'])) + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 27 rows containing non-finite values.

<ggplot: (129525562811)>

ggplot(Chlo, aes(x='Treatment', y=Chlo['Concentration_2'], fill = 'Treatment')) + geom_boxplot(aes(x='Treatment', y=Chlo['Concentration_2'])) + flip_xlabels

C:\Users\jbarreto\Anaconda3\lib\site-packages\plotnine\layer.py:324: PlotnineWarning: stat_boxplot : Removed 27 rows containing non-finite values.

<ggplot: (129525768554)>

# Set max number of rows to visualize
pd.set_option('display.max_rows', 30)
Chlo.groupby(['Treatment'])['Concentration_1'].describe()

	count	mean	std	min	25%	50%	75%	max
Treatment
T1:Water	21.0	478.238095	59.999921	345.0	453.00	478.0	522.00	598.0
T2:AVG_Low	24.0	462.083333	66.202533	313.0	432.25	456.0	517.50	560.0
T3:AVG_Med	24.0	413.125000	77.831654	262.0	368.25	408.0	460.50	548.0
T4:AVG_High	24.0	466.083333	100.919217	237.0	425.50	475.0	536.50	643.0
T5:ETH	24.0	472.583333	56.014685	370.0	429.00	484.5	522.00	560.0
T6:PrhxCa_Low	24.0	478.541667	71.641608	332.0	430.75	494.0	526.75	611.0
T7:PrhxCa_Med	24.0	484.583333	43.852437	427.0	455.75	475.0	498.50	592.0
T8:PrhxCa_High	24.0	470.375000	42.621502	414.0	444.50	462.5	495.75	573.0
T9:GA3	27.0	448.148148	61.484022	313.0	434.00	459.0	487.50	535.0

Chlo.groupby(['Treatment'])['Concentration_2'].describe()

	count	mean	std	min	25%	50%	75%	max
Treatment
T1:Water	21.0	456.190476	75.161572	338.0	402.00	453.0	484.00	617.0
T2:AVG_Low	24.0	482.916667	56.652961	383.0	446.00	491.0	519.25	573.0
T3:AVG_Med	24.0	455.708333	71.975527	281.0	416.25	452.5	516.00	579.0
T4:AVG_High	24.0	452.875000	61.068253	338.0	411.00	456.0	478.00	605.0
T5:ETH	24.0	525.541667	50.280932	421.0	500.00	541.5	567.00	598.0
T6:PrhxCa_Low	24.0	477.041667	52.455761	376.0	446.00	484.0	511.50	592.0
T7:PrhxCa_Med	24.0	509.708333	45.313861	421.0	482.50	497.0	538.25	598.0
T8:PrhxCa_High	24.0	476.041667	67.191795	281.0	462.00	487.5	504.75	598.0
T9:GA3	27.0	481.888889	56.889456	351.0	446.50	491.0	525.50	560.0

Development

GustH = pd.read_csv ('.\CURATED\PGRGH2021_GustHgt_Compiled.csv')
print(GustH.columns)
GustH

Index(['Block', 'Plot', 'Tray', 'Treatment', 'VisShatt', 'Range',
       'Shaken_SPKS', 'Pre-Detached_SEED', 'TOTAL_Undetached', 'Detached_SEED',
       'Undetached_SEED', 'NotesShake', 'AVG_Shatt_SPK', 'AVG_Retent_SPK',
       'AVG_AdjShatt_SPK', 'POT_Yld_SPK', 'PCTG_YldLoss', 'PCTG_YldLoss_SPK',
       'Dry_Unthreshed', 'Dry_Threshed', 'NotesDry', 'WET_wgt', 'SMC_Unthr',
       'Est_Debris', 'Column', 'Row', 'G1_Apr07', 'G2_Apr16', 'G3_Apr19',
       'G4_Apr21', 'G5_Apr23', 'G6_Apr28', 'G7_May03', 'Tallest',
       'AverageHeight', 'AUC_Gust'],
      dtype='object')

	Block	Plot	Tray	Treatment	VisShatt	Range	Shaken_SPKS	Pre-Detached_SEED	TOTAL_Undetached	Detached_SEED	...	G1_Apr07	G2_Apr16	G3_Apr19	G4_Apr21	G5_Apr23	G6_Apr28	G7_May03	Tallest	AverageHeight	AUC_Gust
0	B1	p0001	1	T5:ETH	NaN	NaN	NaN	NaN	NaN	NaN	...	40.0	53.0	57.0	55.0	61.0	65.0	69.0	34.0	25	209.496317
1	B1	p0003	1	T4:AVG_High	NaN	NaN	NaN	NaN	NaN	NaN	...	40.0	54.0	54.0	65.0	65.0	65.0	69.0	52.0	40	209.607428
2	B1	p0005	2	T7:PrhxCa_Med	NaN	NaN	NaN	NaN	NaN	NaN	...	32.0	45.0	52.0	52.0	55.0	59.0	69.0	36.0	26	207.718539
3	B1	p0007	3	T6:PrhxCa_Low	NaN	NaN	NaN	NaN	NaN	NaN	...	32.0	51.0	54.0	57.0	58.0	65.0	69.0	51.0	41	208.385206
4	B1	p0009	3	T3:AVG_Med	NaN	NaN	NaN	NaN	NaN	NaN	...	40.0	45.0	45.0	65.0	53.0	57.0	69.0	59.0	48	208.607428
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
535	B3	p1071	57	T9:GA3	NaN	NaN	NaN	NaN	NaN	NaN	...	32.0	56.0	61.0	65.0	65.0	65.0	69.0	78.0	56	208.940761
536	B3	p1073	58	T6:PrhxCa_Low	2.5	5.0	13.0	0.001	0.920	0.026	...	45.0	53.0	56.0	65.0	65.0	65.0	69.0	57.0	42	210.051872
537	B3	p1075	59	T1:Water	15.0	10.0	14.0	0.042	0.500	0.020	...	40.0	52.0	57.0	65.0	65.0	65.0	69.0	54.0	43	209.385206
538	B3	p1077	59	T7:PrhxCa_Med	2.5	5.0	13.0	0.023	0.798	0.032	...	32.0	45.0	51.0	53.0	53.0	61.0	65.0	46.0	33	207.718539
539	B3	p1079	60	T1:Water	2.5	5.0	12.0	0.000	0.488	0.008	...	45.0	57.0	58.0	65.0	65.0	69.0	69.0	55.0	44	210.496317

540 rows × 36 columns

AUC

# Calculate the area under the curve to the a unique score for development.
GustH['AUC_Gust'] = ( ( np.mean(10 + GustH['G1_Apr07']) / 23 ) + 
                       ( (GustH['G1_Apr07'] + GustH['G2_Apr16']) / 9 ) + 
                       ( np.mean(GustH['G2_Apr16'] + GustH['G3_Apr19']) / 3 ) + 
                       ( np.mean(GustH['G3_Apr19'] + GustH['G4_Apr21']) / 2 ) )

# Set max number of rows to visualize
pd.set_option('display.max_rows', 30)

GustH.groupby(['Treatment'])['AUC_Gust'].describe()

	count	mean	std	min	25%	50%	75%	max
Treatment
T1:Water	58.0	104.131759	0.975262	101.949766	103.421989	104.283100	104.810878	106.838655
T2:AVG_Low	58.0	103.886548	0.951069	101.949766	103.283100	103.783100	104.477544	106.060878
T3:AVG_Med	57.0	103.803568	0.925620	101.949766	103.283100	103.616433	104.505322	106.394211
T4:AVG_High	58.0	103.846318	0.975743	101.949766	103.199766	103.671989	104.616433	105.727544
T5:ETH	58.0	103.844402	0.884106	102.505322	103.310878	103.505322	104.505322	105.616433
T6:PrhxCa_Low	58.0	103.888464	0.959472	102.060878	103.394211	103.616433	104.394211	106.838655
T7:PrhxCa_Med	57.0	103.735342	1.053017	100.060878	103.283100	103.727544	104.505322	105.171989
T8:PrhxCa_High	57.0	103.715848	0.881838	101.949766	103.283100	103.505322	104.394211	105.283100
T9:GA3	58.0	104.325245	0.959394	102.060878	103.533100	104.505322	105.060878	105.838655

GustH_long = pd.melt(GustH, id_vars=['Block', 'Plot', 'Tray', 'Column', 'Row', 'Treatment','Tallest', 'AverageHeight','AUC_Gust'], value_vars=['G1_Apr07','G2_Apr16', 'G3_Apr19', 'G4_Apr21', 'G5_Apr23', 'G6_Apr28', 'G7_May03'], var_name='Date', value_name='Gustavsson')
GustH_long

	Block	Plot	Tray	Column	Row	Treatment	Tallest	AverageHeight	AUC_Gust	Date	Gustavsson
0	B1	p0001	1	1	1	T5:ETH	34.0	25	104.394211	G1_Apr07	40.0
1	B1	p0003	1	3	1	T4:AVG_High	52.0	40	104.505322	G1_Apr07	40.0
2	B1	p0005	2	5	1	T7:PrhxCa_Med	36.0	26	102.616433	G1_Apr07	32.0
3	B1	p0007	3	7	1	T6:PrhxCa_Low	51.0	41	103.283100	G1_Apr07	32.0
4	B1	p0009	3	9	1	T3:AVG_Med	59.0	48	103.505322	G1_Apr07	40.0
...	...	...	...	...	...	...	...	...	...	...	...
3775	B3	p1071	57	6	24	T9:GA3	78.0	56	103.838655	G7_May03	69.0
3776	B3	p1073	58	8	24	T6:PrhxCa_Low	57.0	42	104.949766	G7_May03	69.0
3777	B3	p1075	59	10	24	T1:Water	54.0	43	104.283100	G7_May03	69.0
3778	B3	p1077	59	12	24	T7:PrhxCa_Med	46.0	33	102.616433	G7_May03	65.0
3779	B3	p1079	60	14	24	T1:Water	55.0	44	105.394211	G7_May03	69.0

3780 rows × 11 columns

ggplot(Chlo, aes(x='Treatment', y=np.log10(Chlo['AUC_Gust']), fill = 'Treatment')) + geom_boxplot(aes(x='Treatment', y=Chlo['AUC_Gust'])) + flip_xlabels

<ggplot: (129524148818)>

ggplot(GustH_long, aes(x='Date', y=GustH_long['Treatment'], fill = 'Gustavsson')) + geom_tile() + theme(figure_size=(12,8))

<ggplot: (129431107464)>

# Set max number of rows to visualize
pd.set_option('display.max_rows', 20)
GustH_long.groupby(['Block', 'Treatment']).size()

Block  Treatment     
B1     T1:Water          140
       T2:AVG_Low        140
       T3:AVG_Med        140
       T4:AVG_High       140
       T5:ETH            140
                        ... 
B3     T5:ETH            140
       T6:PrhxCa_Low     140
       T7:PrhxCa_Med     140
       T8:PrhxCa_High    140
       T9:GA3            140
Length: 27, dtype: int64